© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56207
    Prev
    Next
    INDEX
    Explanations

    the notion of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙĩدÙĬ
    -0.08
    ognito
    -0.07
    rik
    -0.07
    ønd
    -0.07
    æݪ并举
    -0.07
    ب
    -0.06
    iop
    -0.06
    áºŃy
    -0.06
    umul
    -0.06
    apyrus
    -0.06
    POSITIVE LOGITS
    jenigen
    0.12
    ÑģÑı
    0.10
    mehr
    0.10
    zelfde
    0.09
    ä¸įæĭĶ
    0.09
    à¥į
    0.09
    ï¸İ
    0.08
    ehr
    0.08
    ection
    0.08
    ãģªãĤīãģļ
    0.08
    Activations Density 0.004%

    No Known Activations